MatthisHoules's picture
Upload tokenizer
7672e2c verified
metadata
license: apache-2.0
tags:
  - generated_from_trainer
base_model: t5-large
model-index:
  - name: t5-large-qdmr-grounded-with-db
    results: []

t5-large-qdmr-grounded-with-db

This model is a fine-tuned version of t5-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1100

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 1
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 20000

Training results

Training Loss Epoch Step Validation Loss
0.2122 0.2312 500 0.1902
0.1786 0.4624 1000 0.1430
0.146 0.6936 1500 0.1148
0.1223 0.9249 2000 0.1092
0.0976 1.1561 2500 0.1100

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1